LLM EXPLORER 61,060 MODELS INDEXED

LaMini GPT 1.5B by MBZUAI

By MBZUAI · 248 downloads

LaMini GPT 1.5B is an open-source language model by MBZUAI. Features: 1.5b LLM, VRAM: 6.3GB, License: cc-by-nc-4.0, LLM Explorer Score: 0.11, Arc: 31.4, HellaSwag: 48.4, MMLU: 29.9.

  Arxiv:2304.14402   Deploy:azure   En   Endpoints compatible   Gpt2   Pytorch   Region:us
Model Card on HF πŸ€—: https://huggingface.co/MBZUAI/LaMini-GPT-1.5B 

LaMini GPT 1.5B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
responding to human instructions
Applications:
text generation applications
Primary Use Cases:
instruction following
Supported Languages 
en (native)
Training Details 
Data Sources:
LaMini-instruction dataset
Data Volume:
2.58M samples
Methodology:
fine-tuning
Model Architecture:
gpt2-xl
LLM NameLaMini GPT 1.5B
Repository πŸ€—https://huggingface.co/MBZUAI/LaMini-GPT-1.5B 
Model Size1.5b
Required VRAM6.3 GB
Updated2026-08-08
MaintainerMBZUAI
Model Typegpt2
Model Files  6.3 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Licensecc-by-nc-4.0
Model Max Length512
Transformers Version4.28.0.dev0
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50258
Torch Data Typefloat32
Activation Functiongelu_new
Errorsreplace

Best Alternatives to LaMini GPT 1.5B

Best Alternatives
Context / RAM
Downloads
Likes
Via 1.5B Core0K / 1.4 GB421
Aragpt2 Base0K / 0.6 GB593733
Aragpt2 Medium0K / 1.5 GB85111
Note: green Score (e.g. "73.2") means that the model is better than MBZUAI/LaMini-GPT-1.5B.